New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI430X run FRED-T5-XL?
Yes — here's how fast and up to what context, with real measured numbers.
FRED-T5-XL on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 5988k | 4218.1-5155.5 t/s | ~7.2-8.9 (slow) |
| Q8 | yes | 6015k | 8436.2-10310.9 t/s | ~14.5-17.7 (slow) |
| Q4 | yes | 6027k | 15064.7-18412.4 t/s | ~25.9-31.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the Instinct MI430X run FRED-T5-XL?▶
Yes. At Q4 it generates ~15064.7-18412.4 tok/s and fits up to 6027k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~25.9-31.6 tok/s.
How much context fits?▶
At Q4, up to about 6027k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.